Training in progress, epoch 1

config.json

@@ -1,13 +1,13 @@
 {
-  "_name_or_path": "distilbert-base-uncased",
+  "_name_or_path": "distilbert-base-uncased-ark",
   "activation": "gelu",
   "architectures": [
     "DistilBertForSequenceClassification"
   ],
   "attention_dropout": 0.1,
-  "dim": 768,
+  "dim": 128,
   "dropout": 0.1,
-  "hidden_dim": 3072,
+  "hidden_dim": 256,
   "id2label": {
     "0": "text1",
     "1": "text2"
@@ -17,17 +17,16 @@
     "text1": 0,
     "text2": 1
   },
-  "max_position_embeddings": 512,
+  "max_position_embeddings": 64,
   "model_type": "distilbert",
-  "n_heads": 12,
-  "n_layers": 6,
+  "n_heads": 4,
+  "n_layers": 3,
   "pad_token_id": 0,
   "problem_type": "single_label_classification",
   "qa_dropout": 0.1,
   "seq_classif_dropout": 0.2,
   "sinusoidal_pos_embds": false,
-  "tie_weights_": true,
   "torch_dtype": "float32",
   "transformers_version": "4.34.1",
-  "vocab_size": 30522
+  "vocab_size": 5000
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1af000f301c455329d2a811881b407caec0c1c7c3237360f777a5c52551aaf9
-size 267854570
+oid sha256:4254632af5dd0c76c925ab0edbad214bdf1a2300f71384a8ee1f3b90f4c922b8
+size 4269078

special_tokens_map.json

@@ -1,7 +1,37 @@
 {
-  "cls_token": "[CLS]",
-  "mask_token": "[MASK]",
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
-  "unk_token": "[UNK]"
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
 }

tokenizer_config.json

@@ -8,7 +8,7 @@
       "single_word": false,
       "special": true
     },
-    "100": {
+    "1": {
       "content": "[UNK]",
       "lstrip": false,
       "normalized": false,
@@ -16,7 +16,7 @@
       "single_word": false,
       "special": true
     },
-    "101": {
+    "2": {
       "content": "[CLS]",
       "lstrip": false,
       "normalized": false,
@@ -24,7 +24,7 @@
       "single_word": false,
       "special": true
     },
-    "102": {
+    "3": {
       "content": "[SEP]",
       "lstrip": false,
       "normalized": false,
@@ -32,7 +32,7 @@
       "single_word": false,
       "special": true
     },
-    "103": {
+    "4": {
       "content": "[MASK]",
       "lstrip": false,
       "normalized": false,
@@ -45,11 +45,15 @@
   "cls_token": "[CLS]",
   "do_lower_case": true,
   "mask_token": "[MASK]",
+  "max_length": 64,
   "model_max_length": 512,
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",
+  "stride": 0,
   "strip_accents": null,
   "tokenize_chinese_chars": true,
   "tokenizer_class": "DistilBertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
   "unk_token": "[UNK]"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e69e379a1ef71471ab5a95c3591f3b18b47f2f91baf26d6f1572cf3add1cdcda
+oid sha256:63b6184d1109c40081f6747472ce8e5814090f264a02f06648debb55aed88f89
 size 4536